New Qwen 3.5 lineup is nothing short of breakthrough! Genuinely impressed with coherence, knowledge and skill that are available on consumer hardware courtesy of @JustinLin610 and the team. All the best in your next adventure! Below are some fun 27b replies.

This week's technology is amazing! Trying tidewave.ai with @Alibaba_Qwen 3 4B as the "brains" of the operation - works out of the box. Just scratching the surface and excited about what I am seeing so far! As a bonus - puts my 3060 through paces. #myelixirstatus

TIL: you can ask @AnthropicAI Claude Code to control your @Zellij_dev as a part of the workflow - very neat. Is there an MCP server for Zellij already - or should I ask Claude to make one? :)

Succumbing to chaos coding trend with Claude Code. Just asked it to build something cool and it built a mini-game that looks quite polished - and the best part - required zero direction :) Fun times. #chaoscoding

Generated on Mac Air with M2 processor in 60s, 5GB peak memory consumption and extremely basic prompt. So many things to experiment with. Thank you for keeping my laptop relevant, @awnihannun :)

It is truly incredible how far ~50 lines of code can get you with the right tools. Extremely simple, Livebook-based chat with local model. Took 15min to put together. Kudos to @livebookdev @AIatMeta @ollama @lebrunel for making magic like this possible! #myelixirstatus

Llama 3 8b is insanely good out of the box. Just doing some casual space exploration in text mode :)

Could be this? Basically `rescue` can convert Erlang exceptions into Elixir ones, while `catch` can't. hexdocs.pm/elixir/1.12/Kerne…